© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 11717
    Prev
    Next
    INDEX
    Explanations

    words and fragments in languages other than English, especially those with diacritics

    oai_token-act-pair · gemini-2.0-flash

    Code/foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.76
    はじめに
    -0.63
    ########.
    -0.60
    bewerken
    -0.59
     Chaco
    -0.59
     Medea
    -0.59
     twij
    -0.58
    ủi
    -0.58
     Winfrey
    -0.58
     hereof
    -0.58
    POSITIVE LOGITS
    mybatisplus
    0.66
     hard
    0.59
    StructEnd
    0.51
     CascadeType
    0.50
    ollectionView
    0.49
     Hard
    0.49
     Sum
    0.47
     sum
    0.47
     last
    0.47
    افظة
    0.46
    Activations Density 6.602%

    No Known Activations